BenchLeader
Stability AIAuto-detected

stablelm-tuned-alpha-7b

Not yet ranked: too few independent results so far. Released 19 Apr 2023.

Blended price
Output speed
First answer
Context
How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.
  1. Reasoning5
  2. Coding8
  3. Human preference5

Benchmark results

One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.

Reasoning

BenchmarkdefaultSource
LMArena Hard Prompts943#348LMArena

Coding

BenchmarkdefaultSource
LMArena Coding1005#341LMArena

Human preference

BenchmarkdefaultSource
LMArena Text953#350LMArena

Composite

BenchmarkdefaultSource
Epoch Capabilities Indexnot in index54.8#235Epoch AI Benchmarking Hub

See also

Data as of 9 Sept 2026. Compare with another model.